Narratological Knowledge for Natural Language Generation

Birte Lnneker
Narratology Research Group Hamburg
Institut fr Germanistik II, University of Hamburg
Von-Melle-Park 6, D-20146 Hamburg
birte.loenneker@uni-hamburg.de
Abstract

Introduction

Story Generation and NLG

This section gives a brief overview of the relationship

between Story Generation (SG) and NLG. Subsection 2.1
describes the architectural gap between SG and NLG.
Subsection 2.2 discusses the contribution of an existing
system to fill that gap. An extended account of work in SG
cannot be provided here. Prez y Prez and Sharples [2004]
compare and evaluate three recent SG systems. For a
discussion of earlier systems, see [Ryan, 1991:233248].

2.1 The Story Generation-NLG Gap

Story Generators aim to produce interesting, understandable, artistic, and creative stories [Turner, 1994:15]. In
doing so, they focus on the story (histoire) representational
domain. For example, the generator MINSTREL [Turner,
1994] achieves not only thematic and consistency goals, but
also dramatic and presentational goals solely by adding
or transforming story events and background information.
The story content is directly mapped onto the output text.
SG faces the difficult problem of finding an interesting
and logically coherent event sequence (story). Less energy
is spent on other tasks, especially at discourse and surface
level. In fact, most implemented SG systems use templates
of different varieties for NLG. Document structuring and
microplanning as NLG processing stages [Reiter, 1994;
Reiter and Dale, 2000:60] are usually skipped in SG, so that
SG and NLG architectures can be confronted as in Figure 1.
Implicit goal: Write coherent narrative
of given genre
Determine content (story), directly
associated with structure (discourse)

Communicative goal

Document planner

Content det.
Doc. structuring

Document plan
Microplanner
(Abstract) content specification

(Abstract) text specification

Template filling

Surface realizer

Surface narrative

Surface text

Figure 1: Story Generation and Natural Language Generation

General NLG

Natural Language Generation (NLG) systems usually focus

on descriptive text types. Narrative structures are underrepresented in NLG. However, they are encountered in
many naturally occurring texts, and not only in fiction.
Often, texts are composed of segments with different
prevailing functions: some are descriptive, some argumentative, others narrative. Therefore, knowledge about narratives
can be useful also for NLG systems that deal with classical NLG tasks. For example, a system that is expected to
describe and compare objects in a museum could include
narrative passages about their use, history or discovery.
The discipline concerned with the structure of narrative
[Barthes, 1966] and narrative discourse [Genette, 1980] is
called narratology. Narratologists distinguish between two
main representational domains of narratives: 1. the story
(histoire) as the totality of the narrated events, abstracted
from their disposition in the text; and 2. the discourse
(rcit) that narrates them [Genette, 1988:13].
Narratology has identified a number of descriptive
parameters. As can be seen from the explanations in Table 1
(see Appendix), many parameters describe phenomena that
relate discourse to story in a specific way.
This paper envisages an NLG system with improved
abilities to deal with narrative discourse. Section 2 summarises the relation between Story Generation and NLG. In
Section 3, an architecture for a narratologically enhanced
NLG system is proposed. Section 4 outlines one of the descriptive parameters, illustrating the kind of knowledge that
can be acquired from narratology. Section 5 exemplifies the
domain modelling, a prerequisite for modelling narratological knowledge. Section 6 formalises the selected narratological parameter, discusses its mapping onto discourse
graphs used in NLG, and exemplifies its use in a system.
Section 7 concludes the paper and mentions future work.

Traditional SG

The paper proposes an architecture for advanced

NLG systems that handle narratives. Special
attention is paid to document planning. Domain
modelling and meta-knowledge modelling for a
narratological structurer are exemplified.

2.2 STORYBOOK

The existence of a gap between SG and NLG has also been

discussed by Callaway and Lester [2002]. To remedy the
situation, they implemented STORYBOOK, an architecture
for narrative prose generation [2002:228]. The input to
STORYBOOK must be a narrative stream that reflects the
orderly progression of events, descriptions and states
[Callaway and Lester, 2002:231], produced by a hypothetical Story Generator. STORYBOOK expects this input stream
to contain so-called narrative primitives that specify scene
changes and other aspects such as:
narrative person and focalization (person, omniscience [Callaway and Lester, 2002:221]);

Narratological aspects influence on all architectural modules

[Reiter, 1994] or representation levels [Cahill et al., 2000]
of NLG. The most important decisions of a narratologically
enhanced system concern the document planner with its
content determination and document structuring subtasks (Subsections 3.13.2). Microplanning and surface
realization (Subsection 3.3) are supposed to resemble classical NLG processes. As further explained below, the architecture of the envisaged system corresponds to Figure 3.

details about dialogue realization (e.g. whether an

inquit phrase such as he said should precede, follow
or interrupt direct speech, or whether it should be
omitted altogether [Callaway and Lester, 2002:225]).
Person and focalization are classical narratological parameters [Genette, 1980]. It is not clear from Callaway and
Lester [2002] how many different values STORYBOOK actually implements for these parameters; their example tale is
invariably rendered by a third person disembodied narrator [2002:230]. The question of whether or not a character utterance is to be provided with an inquit phrase is
sometimes subsumed under the narrative distance parameter
(cf. Table 1): Direct speech framed by inquit phrases is definitely considered as imitating, but the highest level of imitation is achieved by the reproduction of unframed direct
speech [Fludernik, 2005; Genette, 1988:56].
In STORYBOOK, many decisions concerning discourse
still lie with the Story Generator that is supposed to produce
a stream with narrative primitives. STORYBOOK itself neither decides about narrative person, focalization, or distance
for any given passage, nor is it concerned with any other
narratological parameters listed in Table 1. Rather,
STORYBOOK focuses on microplanning and surface phenomena with special attention to features particular to narrative. The architectural contribution of STORYBOOK can
thus be seen as reducing the gap between SG and NLG to
approximately the microplanner level, where STORYBOOK,
as a specialized NLG system, takes over from a hypothetical
Story Generator (see Figure 2).

Implicit goal: Write coherent narrative

of genre: fairy tale
Determine content (story), decide about

Narrative stream

person, focalization, speech reproduction

Hypothetical SG

Microplanner

Surface realizer
Surface text

Figure 2: Story Generation and STORYBOOK

StoryBook

(Abstract) text specification

Narratology for NLG

Story Generator
Determine content
(story) and
part of structure
(esp. causality)

Narratological structurer
Vary (order, person,
point of view,...);
create discourse
representation

Abstract
content
repre
sentation

NLG
Document plan
Microplanner
(Abstract) text specification

Goal: Write coherent narrative

of given genre

Surface realizer
Surface text

Figure 3: Narratologically enhanced Story Generation-NLG system

3.1 Content Determination

In a narratologically enriched NLG system, a narrative
content determination module might be implemented as a
Story Generator. The Story Generator decides
what it considers to be a minimal story [Prince, 1973],
what it considers a good story (cf. Subsection 2.1),
how to select the content that represents the story:
events, participants, and their relations.
However, if narratological discourse parameters are to be
applied, certain story events or participants are required. For
example, the narrative levels parameter presupposes the
existence of at least one NARRATING action among the story
events of the (first) narrative (see Sections 46).
This means that an entirely data-driven, pipelined process
where content determination precedes document structuring
[Reiter and Dale, 2000:111] will not use the full potential of
a narratologically enhanced document planner. Rather, the
content determination module (the Story Generator) should
be able to satisfy constraints issued by the document
structurer. These constraints might well take the form of
modification requests after a first output attempt of the Story
Generator. Therefore, a hypothesis-driven architecture in
which the system switches back and forth between content
determination and document structuring seems well suited
for the task at hand (see the double arrow in Figure 3).

3.2 Document Structuring

In the envisaged architecture, the document structurer
receives the narrative content representation from the Story
Generator. In its simplest form, this input is a sequence of
events together with their participants. The structurer shares
a domain model with the Story Generator, where the
semantics of events and participants are represented.

By default, the incoming event sequence is considered as

corresponding to a discourse related by the NarrativeSequence discourse relation1 (for discourse relations, cf. Subsection 6.3). The sequence might have additional internal
structure, because most Story Generators represent consequences of events and/or episodes, and therefore some kind
of causality [e.g. Gervs et al., 2004; Prez y Prez and
Sharples, 2004; Turner, 1994].
Combining this information with information from the
ontology and with narratological knowledge, the narratological document structurer creates variation in discourse.
Most narrative parameters presented in Table 1 influence on
this representational domain. Amongst others, the Narratological Structurer can perform the following tasks, some
of them in interaction with the Story Generator:
modify the order of events or episodes, tag the shifted
elements as flashbacks or flashforwards, and accordingly modify the discourse relations (a Cause relation
might become an Explanation relation because of the
inverted event order);
create ellipsis by suppressing events or episodes that
the reader might as well infer;
add or remove narrative levels (Sections 46);
decide about point of view and focalization for the
entire narrative or, rather, for certain episodes, and accordingly present or suppress events and relations.
The produced document plan contains discourse relations
and narratological information for nodes and leaves, which
can be further used in microplanning and surface realization.

3.3 Microplanning and Surface Realization

The microplanner performs lexicalisation and aggregation
and generates referring expressions. Besides the usual
constraints, it respects narratological contraints. For example, certain values of focalization and point of view can
cause unusual referring expressions: personal pronouns
might be used for initial reference [Harweg, 1968: 163
166], or indefinite referring expressions for subsequent
reference [Ushie, 1986; Wiebe and Rapaport, 1988]. The
choice of vocabulary, tense, and syntactic complexity can as
well depend on narratological factors.
The surface realizer turns the microplanner output into
natural language text. See [Callaway and Lester, 2002:224]
for narrative-related issues in surface realization.

The Narrative Levels Parameter

The narrative levels parameter will be used to illustrate the

kind of knowledge that can be acquired from narratology for
integration into a narratologically enhanced NLG system.
Narratives can consist of different levels: There are tales
within tales within tales [Barth, 1984]. Genette [1988:85]
illustrates this phenomenon by a figure similar to Figure 4,
1
Similar to the relations Narration [Asher and Lascarides,
2003:162165] or Occasion [Hobbs, 1990:8689].

b
j

i
Figure 4: Narrative levels

in which person i produces an utterance a that contains the

production of another utterance b by person j. Talking about
narratives, the persons in Genettes drawing correspond to
narrative instances (narrators). Narrative instance i might
not be identified by any referring expression throughout the
utterances produced by i (and j): i can be absent from the
story or heterodiegetic [Genette, 1980:244245]. Narrative
instance j, on the other hand, necessarily has to be identical
to a character in story a. Finally, j might be absent (or not)
from the inner narration b that he himself produces (see
Table 1 on Person).
The generation of a narration within a narration presupposes the existence of a NARRATING action in the outer
narration: in Figure 4, a NARRATING action (where j tells b)
occurs within outer narration a.2 Therefore, before narrative
levels will be modelled in detail (Section 6), Section 5 will
be concerned with a definition of NARRATING.
Genettes [1980:244] considerations suggest that narrative levels is one of the simpler narratological parameters.
For example, he claims that any narrative can be converted
into an inner narration by adding presentational outer narrations [Genette, 1988:95]. It should thus be possible to
enable a generation system to create narrativel levels.

5
This

NARRATING and Related Frames

section

proposes

representation

structures for
especially
is considered to represent structured knowledge about a given concept. In terms of NLG tasks, this modelling corresponds to
setting up part of a domain model for content determination
[Reiter and Dale, 2000:8689].
The modelling is supported by concordances from the
German DWDS corpus.3 Contexts of verb forms of erzhlen
(tell; narrate) were investigated, because they evoke the
target frame NARRATING. As DWDS texts are of several
types, the results reflect general (not only literary) language
use. The analysed corpus material stems from texts published between 1990 and 1999. The modelling is also partly
inspired by the SUMO4 upper ontology [Niles and Pease,
2001]. SUMO does not yet include the NARRATING concept.
NARRATING (Subsection 5.1) and related frames,
the NARRATED frame (Subsection 5.2). A frame

5.1 The NARRATING Frame

The NARRATING frame is an indirect subframe of ACTION.
Narratological theories [Chatman, 1978:4445] agree with
2
Inside vs. outside narrations [Barth, 1984:233] are also
called framed vs. framing or embedded vs. embedding.
3
http://www.dwds.de [Query date: 24 January, 2005].
4
http://ontology.teknowledge.com/ [10 March, 2005].

current ontologies like SUMO on the fact that an action is

performed intentionally by a cognitive agent. The NARRATING frame thus inherits an Agent slot which I relabel
NarrativeInstance for better orientation (cf. Table 5).
The NARRATING frame is related to other frames subsumed under the superframe COMMUNICATION_ACTION.
That superframe represents an action in which typically at
least two participants exchange messages. In the present
investigation, NARRATING actions are assumed to express
this content linguistically; therefore, NARRATING is here also
a subframe of LINGUISTIC_COMMUNICATION (cf. Figure 5).
In the NARRATING frame, the content is represented as
complex filler of the Narrated slot; a more detailed
modelling of the NARRATED frame follows in Subsection
5.2. NARRATING is a special subframe of COMMUNICATION_ACTION insofar as it usually restricts the direction of
the information flow between the participants: One of them
is the (main) producer, the other one the (main) recipient of
NARRATED. The respective participant slots are the above
mentioned NarrativeInstance, and the Addressee. Typically, the Addressee or narratee [Genette, 1980] is a cognitive agent different from NarrativeInstance. Nevertheless,
the current model also allows the same individual to act
simultaneously as both NarrativeInstance and Addressee:
cognitive agents may tell a story to themselves.
Comments and questions produced by the Addressee,
concerning the Narrated, deserve some attention. The present conceptualization considers that even if comments and
questions interrupt of the flow of Narrated, they do not
necessarily mark the end of a NARRATING action (see also
Subsection 5.2).
Some other slots of NARRATING are inherited from the
ACTION or EVENT frames. In the DWDS corpus material (cf.
Table 2, Appendix), examples of fillers of Motivation,
Consequence/Aim, ParallelEvent, Time, Place, and Manner are encountered. Typically, one of the Consequences of
NARRATING is a change of the Addressees mental state: the
Narrated is added to her or his knowledge. This consequence seems to belong to the lexico-semantic knowledge
about NARRATING or, probably, COMMUNICATION_ACTIONS
in general, and is rarely mentioned explicitly in texts.
Table 3 gives an overview of the NARRATING frame. It
also maps slot names on binary relation labels and formulates restrictions for the fillers. However, as a representation
of a conceptual entity, it does not specify linguistic restrictions such as addressee-oriented, non-message-oriented
which are considered to hold language-specifically for individual verbs [Bateman et al., 1994]. For the use in a specific
NLG system, the frame and its slots thus need to be mapped
onto the lexicon used by that system during lexicalisation.

5.2 The NARRATED Frame

A text can refer to different aspects of what is narrated in a
NARRATING action. Hence, instead of introducing further
slots within the NARRATING frame, the filler of Narrated
will itself be represented as a frame (cf. Table 4, Appendix).
One way of referring to the NARRATED_LINGUISTIC_MESSAGE, abbreviated as NARRATED , is to mention the Text-

Event (Process)
Happening
...

Action

Experiencing

...

...

CommunicationAction
produces(LinguisticMessage)

Reporting

LinguisticCommunication

Narrating

Committing

Directing

...
...
...

produces(NarratedLinguisticMessage)

Figure 5: Frame hierarchy containing NARRATING

NARRATING
Slot
Relation
NarrativeInstance
isCausedBy
Narrated
produces
Addressee
isAddressedTo
Motivation
isMotivatedBy
Consequence/Aim
causes
ParallelEvent
overlapsWith
Time
happensAtTime
Place
locatedAt
Manner
is
Table 3: The NARRATING frame

Filler Restriction
CognitiveAgent (> 0)
Narrated (1)
CognitiveAgent (>= 0)
AbstractEntity (>= 0)
Event (> 0)
Event (>= 0)
TimePosition (> 0)
PhysicalEntity (> 0)
Attribute (>= 0)

Type of the narrated material. Typically, this is a literary

genre, or one of its parts. Further, the NARRATED uses a
MessageSupport, which might be written (e.g. book, letter), spoken (e.g. speech, song) or thought (e.g. dream).
Thought seems to lend itself to somewhat problematic subdivisions; see e.g. [Genette, 1980:231] on retrospections.
The abstract content of NARRATED is represented linguistically through a LinguisticSurfaceForm. As can be seen
from the DWDS corpus, the LinguisticSurfaceForm occurs as a new sentence or clause, and can be more or less
direct. Research on the reproduction of speech is an area
of both narratology and linguistics. Usually, the forms direct
speech (D in Table 4), free indirect speech and indirect
speech (I in Table 4) are distinguished in increasing order of
narrative distance (see Table 1) [Fludernik, 2005].
Comments and questions produced by the Addressee of a
NARRATING action, concerning the Narrated, should also be
part of the LinguisticSurfaceForm: Metaphorically speaking, they might be seen as discursive catalysts or parasites of
that surface form.
Finally, the Topic slot of the NARRATED frame is typically filled by sentence constituents like objects or prepositional phrases. Since these constituents can themselves be
complex, the topic might be quite detailed, taking the form
of a summary. Still, it does not provide access to the
original linguistic surface form. With respect to narrative,
this category is also referred to as narrative report of
discourse or content summary [Fludernik, 2005].
Figure 6 illustrates the knowledge modelled by
NARRATED and related frames.

NarratedLinguisticMessage
Relation
isOfTextType
uses
hasForm
isAbout

Filler Restriction
MsgSupport
TextType
Written
Thought
MessageSupport
Spoken
LinguisticSurfaceForm
Topic

LinguisticSurfaceForm
DirectLSF

represents(AbstractContent)

FreeIndirectLSF

IndirectLSF

Figure 6: The NARRATED_LINGUISTIC_MESSAGE frame

At a meta-level, the NARRATED frame can be mapped

onto representation structures of the envisaged system that
combines SG and NLG (cf. Figure 3 above). The TextType
is implicitly given in the goal of the Story Generator; also
the Topic or a topic restriction is often given at this stage.
The Support is, depending on the stage of processing, some
digital entity, written (printed), or possibly speech. The AbstractContent is the abstract output of a Story Generator
(the product of content determination). The LinguisticSurfaceForm corresponds to the final NLG output based on
this abstract content. Using knowledge and reasoning procedures, a system might additionally or alternatively summarise AbstractContent into a phrase that represents Topic.

Representing Narrative Levels

This section is concerned with describing a formalism that

should enable a discourse planner to handle narrative levels
(see Section 4). Via the formalism, the system can be told
how many levels a generated narrative should have,
which narrative instance should be the direct
mediator to the reader, and
how outer and inner narrations, or parts thereof,
should follow each other in discourse.
The basic ingredients for the formalism (Subsection 6.1)
are applied to a description of example constellations (Subsection 6.2) and mapped onto discourse relations (Subsection 6.3). Subsection 6.4 briefly exemplifies the cooperation
between Story Generator and Narratological Structurer.

6.1 Basic Ingredients: Classes and Relations

Three classes and two relations need to be modelled to
represent possible structures of global narratives with
respect to their levels.
NARRATION
An instance of NARRATED is a NARRATION if its LinguisticSurfaceForm is of the subtype DirectLinguisticSurfaceForm (and is, as such, explicitly present in the output text).
This narratological constraint correctly excludes from
opening a new narrative level such NARRATING actions
which are merely mentioned, or whose NARRATED is
reproduced indirectly.

NARRATIVE_INSTANCE
A NARRATIVE_INSTANCE is a cognitive agent that occupies
the agent role (NarrativeInstance slot) of a NARRATING
action. Neither the instance itself nor the action needs to be
referred to directly in the surface form of any NARRATION.
For example, if i isA NARRATIVE_INSTANCE, the variable
i is not necessarily resolved against a character name.
toldBy(NARRATION, NARRATIVE_INSTANCE)
The relation toldBy(a,i) holds if there is a NARRATING action
x, a NARRATION a and a NARRATIVE_INSTANCE i such that
both isCausedBy(x,i) and produces(x,a) are true (Table 3).
toldIn(NARRATION, NARRATION)
ToldIn(b,a) or b is told in a holds if there is a NARRATION
b, a NARRATION a, and a NARRATING action x such that:
a is not b;
a is an event sequence such that one of its events is x;
produces(x,b).
DISCOURSE_SEQUENCE
A DISCOURSE_SEQUENCE is an ordered list of variables
standing for different NARRATIONS, as they sequentially occur within the discourse of a global narrative. In a DISCOURSE_SEQUENCE, the same variable may appear more
than once: for example, an outer narration can frame an
inner narration at the start and the end of a discourse.
Variables for separated parts of the same narration receive
numbered subscripts (see a1 and a2 in Figure 7 below).

6.2 Example Constellations

Type 0: Zero-Instantiation
Zero instantiation of the narrative levels parameter occurs if
there is no change in level. There is only one narration, told
by a narrative instance. An example of this type is the fable
The Fox and the Crow by Aesop, because neither the fox
nor the crow produce any narrations. The instantiation of the
classes and relations corresponds to the scenario in Table 5.
I am not aware of any Story Generator (cf. Section 2) that
exceeds the zero instantiation. This would mean that contemporary Story Generators ignore narrative levels.
Type 1: Outer and one Inner Narration
A typical pattern of Type 1 is as follows: An outer narration
contains a NARRATING action whose agent is a narrative
instance different from that of the outer narration. The NARRATED of this action is the inner narration. After the NARRATING action, the rest of the outer narration is told (Table 6).
An example is Heart of Darkness (1902) by Joseph
Conrad. A homodiegetic narrative instance i (= I) tells
outer narration a, while j (= Marlow) tells inner b:
a1

b
j

a2

b
a

Figure 7: Narrative levels and discourse sequence

Classes and Relations

Instantiation
Narration
a
NarrativeInstance
i
Attribution of NarrativeInstance toldBy(a,i)
Attribution of Narration
-Sequence
discourse_sequence=[a]
Table 5: Zero-Instantiation of Narrative Levels
Classes and Relations
Instantiation
Narration
a,b
NarrativeInstance
i,j
Attribution of NarrativeInstance toldBy(a,i), toldBy(b,j)
Attribution of Narration
toldIn(b,a)
Sequence
discourse_sequence=[a1,b,a2]
Table 6: One Inner Narration; Framing Outer Narration

novel Der goldne Spiegel (The golden mirror, 1772) by

Christoph Martin Wieland, for which a structure with three
opening narrations leading to the innermost narration d,
has been identified6 (cf. Table 10, Appendix).
At least equally common are inward extensions of the
levels. While several NARRATING actions within one and the
same outer narration are considered to produce parallel
inner narrations at the same level, further levels are added
when a narration is produced within an inner narration. In
The 1001 Nights, Scheherazade entertains King Shahryar
with parallel inner narrations. In these narrations, the characters sometimes tell one another stories, which are inner
narrations at the next level. Table 11 (Appendix) shows a
simplified version of The 1001 Nights, in which Scheherazade (j) tells only three stories (b,c,d). The third level is
added by narration e, told by a character (k) of narration d.

6.3 Discourse Graphs

[a1 toldBy i] there was nothing else to do till the end of
the flood; [...] we knew we were fated [...] to hear about one
of Marlow's inconclusive experiences.
[b toldBy j] I don't want to bother you much with what
happened to me personally, [comment by i] he began,
showing in this remark the weakness of many tellers of tales
[...]; [b toldBy j] yet to understand the effect of it on me
you ought to know how I got out there, [...], how I went up
that river to the place where I first met the poor chap. [...]
[b toldBy j] I had then, as you remember, just returned
to London [...].5
The implicit inquit phrase he began [...] is a comment
by i concerning the Manner of NARRATING. It is not modelled in the discourse_sequence (see also Subsections 5.1
5.2 on comments). The closing part of outer narrative a in
Heart of Darkness is very short (cf. Figure 8, Appendix).
Type 1 has some variants. For instance, an outer narration
might not be resumed at the end of the discourse (Table 7,
Appendix), as in Abb Prvosts Manon Lescaut (1731). In
contrast, an outer narration (here: b) might manifest itself in
discourse only after the NARRATED (here: a) produced in the
NARRATING action it contains (Table 8, Appendix). Philip
Roths novel Portnoy's Complaint (1969) shows this pattern.
Yet another variant occurs when the narrative instances of
outer and inner narration are identical (Table 9, Appendix).
An example is Balzacs Sarrasine (1831), where a homodiegetic narrator (i) tells a first narration (a) to an unknown addressee (the reader). In the course of a, a NARRATING action is performed by i himself, but with a different
addressee, namely a character in a (cf. Figure 9, Appendix).

The basic assumption underlying discourse graphs is that

discourse relations (e.g. [Mann and Thompson, 1988;
Hobbs, 1990:83111; Asher and Lascarides, 2003]) exist
between discourse segments, where a segment is either a
proposition or a graph consisting of already related propositions. Most theories assume that a limited set of discourse
relations covers all semantic links that might exist between
discourse segments.
Based on the status of segments they relate, multinuclear
and nucleus-satellite discourse relations can be distinguished. The definition of nuclearity by Mann and Thompson [1988:266] is centered around the notions of comprehensibility (a text is less understandable if a nucleus is
deleted), substitutability (satellites can more easily be
replaced) and writer's purpose (nuclei are more essential).
Similarly, Hobbs [1990:104] subdivides discourse relations
into coordinating and subordinating.
There are correspondences to narratological theory (e.g.
[Barthes, 1966; Pavel, 1985; Chatman, 1978]). Chatman
subdivides events, as constituting elements of story, into
kernels and satellites. Kernels cannot be deleted without
disturbing the logic of the plot. Satellites contribute first of
all aesthetically, so that their deletion is logically possible.
A difference lies in the size of the analysed segments.
Linguistically inspired theories include propositions
(clauses) as basic level, but descriptions using these theories
often stop at the level of one or several paragraphs (an exception is [Longacre, 2003]). Narratological analyses usually concentrate on larger segments, represented by paraphrases of their propositions [Chatman, 1978:54].

Other Types: More Than Two Narrations

More than two NARRATIONS can easily be combined
extending the patterns presented above.
Common outward extensions of levels include explicit
introductory or closing NARRATING actions, often produced
on written support by (fictional) editors, translators or
discoverers of the inner narration. An example is the

Discourse Graphs for Type 1 Narrative Levels

To a certain degree, the narratological description of narrative levels constrains which relations might hold between
narrations of a levelled global narrative. Still, it does not
completely disambiguate the global discourse structure.
In fact, in a typical Type 1 narrative (Table 6), the inner
narration b might be related in two competing ways to nar-

5
http://www.online-literature.com/conrad/heart_of_darkness/
[10 March, 2005].

6
By Jrg Schnert in FGN Forum Narratologie
(http://www.narrport.uni-hamburg.de/) on 21 December, 2004.

ration a. The first analysis relates a and b based on a local,

lexical consideration: a NARRATION is regarded as an argument of the verb phrase that evokes NARRATING. This is
illustrated by Example (1). If NARRATED TextType filler
(e.g. a story) is present in a sentence, the English verb tell
allows an implicit LinguisticSurfaceRealization (1a). This
initially underspecified argument of tell might then be
realized in a subsequent sentence (1b), so that an Elaboration relation holds between (1a) and (1b). In nucleus-satellite terms, (1a) is a nucleus elaborated by (1b).
(1)
a. [a toldBy i] John told a story to Mary. b. [b
toldBy j] I was seventeen years old, and [...].
The proposed analysis is in line with Asher and
Lascarides [2003:285], who identify an Elaboration relation
between the propositions (2a) and (2b) of Example (2).
(2)
a. John made a promise to Mary. b. He would
phone her.
The possibility that the resulting discourse graph (Figure
10) indeed holds for a global narrative increases if the
NarrativeSequence representing narration b is relatively
short. This also confirms that in these cases, the DirectLinguisticSurfaceRepresentation of the content of b is an
aesthetical choice rather than a plot-logical necessity.
The presented analysis based on local features does not
always seem globally appropriate as well. Outer narrations
often set the background for a (longer) inner narration at the
start of the discourse_sequence, and draw conclusions,
interpret or evaluate it at the end. Figure 11 shows the
corresponding graph, in which the segment representing
narration b is nucleus of two relations.7 This corresponds to
a schema identified by Mann and Thompson [1988:247].
Danlos [2004:130] presents similar double-nuclear structures (factorized nuclei) at the sentence level.
Both presented graphs are plausible. The final choice for
a given global narrative depends not on narratological discourse description alone, but on story contents as well.

6.4 Processing Examples

This subsection briefly sketches two examples of how the
Story Generator and the Narratological Structurer (cf. Figure 3) could cooperate during the creation of typical Type 1
narrative levels (cf. Subsection 6.2).
Adding an Outer Narration
The Story Generator creates Story A. Respecting the conditions for a Type 1 narrative, the Narratological Structurer
requests an additional Story B, with some restrictions:
B is shorter than A;
B contains a NARRATING event.
The Story Generator generates Story B. This might be a
minimal story consisting of the events MEETING (of characters c1 and c2), NARRATING (of a story by c1), REACTION
(of c2). Upon receipt of B, the Narratological Structurer fills
7

At a global level, the Background relation can be compared

only in a very abstract way to the definitions given by Asher and
Lascarides [2003:165168] or Mann and Thompson [1988:273].

"Outer Narration" a
NarrativeSequence
a1
NarrativeSequence

Elaboration

a2
NarrativeSequence

Satellite
"Inner Narration" b
NarrativeSequence
Nucleus
[130] [31]John told:

[32] [33] [34]

[3540]

Figure 10: Discourse Graph 1 for Type 1, Framing Outer Narration

"Outer Narration" a
NarrativeSequence
Interpretation/
Evaluation/...

Background

Satellite Nucleus
Nucleus Satellite
a2
a1
"Inner Narration" b
NarrativeSequence
NarrativeSequence
NarrativeSequence
[13]

[412]

[1315]

Figure 11: Discourse Graph 2 for Type 1, Framing Outer Narration

Story A into the Narrated slot of the NARRATING event in

B, tags it as direct speech for the subsequent processing
modules, and arranges all contents into a discourse tree
corresponding to Figure 11. Story A has become an inner
narration and a nucleus, Story B is the outer narration.
Adding an Inner Narration
The Story Generator creates Story A which contains a
NARRATING event. The Narratological Structurer requests an
additional Story B, with the following restrictions:
B is shorter than A;
the contents of B illustrate a part of A, for example an
event present in A, or a character trait of the NarrativeInstance of the NARRATING event.
The Story Generator generates Story B. For instance, the
illustration of A might be achieved by similarity: if Story A
contains a CRIME event (e.g. KIDNAPPING), Story B can contain a CRIME event as well (e.g. ROBBERY). The Narratological Structurer now fills the new Story B into the Narrated
slot of the NARRATING event in A, tags it as direct speech,
and arranges all contents into a discourse tree, this time
corresponding to Figure 10. Story A has become an outer
narration, Story B is the inner narration and a satellite.

Conclusions and Future Work

The proposed system architecture combines Story Generation, narratological structuring and traditional NLG components into an advanced NLG system for the production of
narratives. Starting with the narrative levels parameter, domain modelling and meta-knowledge modelling for the
Narratological Structurer were exemplified. Future work
will include comments by narrators, some of which can be
compared to global level discourse markers.
Further narratological parameters will be modelled, and
constraints will be formulated for their accumulation. A
cognitive approach might work out their aesthetical effects.

For example, certain receptional states or strategies could be

identified as prototypically activated, enabled, or blocked
by a given combination of narratological parameter instantiations. Finally, content-related studies will lead to concrete
proposals for the interaction between a Narratological Structurer and one of the existing Story Generators.

Acknowledgments
This research is supported by DFG (German Research
Foundation) grant ME 1546/2-1. Thanks go to all members
of the Narratology Research Group Hamburg, especially to
Rolf Krause, Jan Christoph Meister and Stefanie Thiedig, as
well as to three anonymous reviewers for their comments.

References
[Asher and Lascarides, 2003] Nicholas Asher and Alex Lascarides. Logics of Conversation. Cambridge University
Press, Cambridge and New York, 2003.
[Barth, 1984] John Barth. The Friday Book, chapter Tales
Within Tales Within Tales, pages 213252. John
Hopkins University Press, Baltimore and London, 1984.
[Barthes, 1966] Roland Barthes. Introduction l'analyse
structurale du rcit. Communications, 8:127, 1966.
[Bateman et al., 1994] John Bateman, Bernardo Magnini
and Fabio Rinaldi. The Generalized {Italian, German,
English} Upper Model. In Proceedings of the ECAI-94
Workshop on Implemented Ontologies, pages 3545,
Amsterdam, August 1994.
[Cahill et al., 2000] L. Cahill, C. Doran, R. Evans, R. Kibble, C. Mellish, D. Paiva, M. Reape, D. Scott, and N.
Tipper. Enabling Resource Sharing in Language Generation: An Abstract Reference Architecture. Technical
Paper, MITRE, 2000.
[Callaway and Lester, 2002] Charles B. Callaway and James
C. Lester. Narrative Prose Generation. Artificial Intelligence, 139(2):213252, August 2002.
[Chatman, 1978] Seymour B. Chatman. Story and Discourse. Narrative Structure in Fiction and Film. Cornell
University Press, Ithaca, NY, 1978.
[Danlos, 2004] Laurence Danlos. Discourse Dependency
Structures as constrained DAGs. In Proceedings of the
5th SIGDIAL Workshop on Discourse and Dialogue,
pages 127135, Cambridge, MA, April 2004.
[Fludernik, 2005] Monika Fludernik. Speech Representation. In David Herman, Manfred Jahn and Marie-Laure
Ryan, editors, Routledge Encyclopedia of Narrative
Theory, pages 558563. Routledge, London, 2005.
[Genette, 1980] Grard Genette. Narrative Discourse. An Essay in Method. Cornell University Press, Ithaca, NY, 1980.
[Genette, 1988] Grard Genette. Narrative Discourse Revisited. Cornell University Press, Ithaca, NY, 1988.
[Gervs et al., 2004] Pablo Gervs, Beln Daz-Agudo, Federico Peinado, and Raquel Hervs. Story Plot Genera-

tion based on CBR. In Applications and Innovations in

Intelligent Systems XII (at AI-2004), pages 3346,
Cambridge, UK, December 2004.
[Harweg, 1968] Roland Harweg. Pronomina und Textkonstitution. Fink, Mnchen, 1968.
[Hobbs, 1990] Jerry R. Hobbs. Literature and Cognition.
CSLI, Stanford, CA, 1990.
[Longacre, 2003] Robert E. Longacre. Holistic Textlinguistics. Electronic working paper, SIL International, 2003.
[Mann and Thompson, 1988] William C. Mann and Sandra
A. Thompson. Rhetorical Structure Theory. Toward a
Functional Theory of Text Organisation. Text, 8(3):243
281, 1988.
[Niles and Pease, 2001] Ian Niles and Adam Pease. Towards
a Standard Upper Ontology. In Proceedings of the 2nd
International Conference on Formal Ontology in Information Systems, pages 29, Ogunquit, ME, October 2001.
[Pavel, 1985] Thomas G. Pavel. The Poetics of Plot. The
Case of English Renaissance Drama. Manchester University Press, Manchester, 1985.
[Prez y Prez and Sharples, 2004] Rafael Prez y Prez and
Mike Sharples. Three computer-based models of storytelling: BRUTUS, MINSTREL and MEXICA. Knowledge-Based Systems, 17:1529, 2004.
[Prince, 1973] Gerald Prince. A Grammar of Stories. An
Introduction. Mouton, The Hague and Paris, 1973.
[Reiter, 1994] Ehud Reiter. Has a Consensus NL Generation
Architecture Appeared, and is it Psycholinguistically Plausible? In Proceedings of the 7th International Workshop
on Natural Language Generation, pages 163170, Kennebunkport, ME, June 1994.
[Reiter and Dale, 2000] Ehud Reiter and Robert Dale. Building Natural Language Generation Systems. Cambridge
University Press, Cambridge, 2000.
[Rumelhart, 1975] David Rumelhart. Notes on a Schema for
Stories. In Daniel G. Bobrow, editor, Representation and
Understanding. Studies in Cognitive Science, pages 211
236. Academic Press, New York et al., 1975.
[Ryan, 1991] Marie-Laure Ryan. Possible Worlds, Artificial
Intelligence, and Narrative Theory. Indiana University
Press, Bloomington and Indianapolis, 1991.
[Turner, 1994] Scott R. Turner. The Creative Process: A
Computer Model of Storytelling. Lawrence Erlbaum,
Hillsdale, 1994.
[Ushie, 1988] Yukiko Ushie. Corepresentation. A Textual
Function of the Indefinite Expression. Text, 6(4):427
446, 1986.
[Wiebe and Rapaport, 1988] Janyce M. Wiebe and William
J. Rapaport. A Computational Theory of Perspective and
Reference in Narrative. In Proceedings of the 26th
Annual Meeting of the Association for Computational
Linguistics, pages 131138, Buffalo, NY, June 1988.

A Appendix
Parameter
Time: Order

Explanation
Sequence in which events are told, in comparison with the sequence in which they actually happened. In
synchrony, the event sequence in discourse corresponds to the sequence of the story. Anachronies can take the
form of flashbacks (retrospectives) or flashforwards (anticipations).
Time: Speed
Relation between story time and discourse time. Congruence exists probably only in single scenes; otherwise
timelapses (accelerations), time jumps (ellipsis), time expansions (decelerations), or pauses are used to achieve
different degrees of expliciteness and emphasis.
Time: Frequence
Relation between the number of times a (similar) event happened, and the number of times an event is told. The
following realizations are distinguished: singulative (one-to-one relation), repetitive (recount several times what
happened once), and iterative (recount once what happened several times).
Mood: Distance
Combination of amount of information conveyed and narrator intrusion. Stereotypically, detailed information and
low narrator participation indicate imitation or direct dramatic mode, as opposed to a distant, mediated
narrative mode. This parameter also affects the way in which speech is reproduced.
Mood: Focalisation Accessibility of knowledge needed to select story events for presentation in discourse. If a narrative instance
disposes of unrestricted knowledge of the story world, it uses external focalization; if the knowledge is restricted to
a character's field of perception, focalization is internal.
Mood:
Spatial, temporal, and ideological points of view from which events are described. Events can be described from
Point of view
the point of view of different characters. This parameter covers more aspects than focalization.
Voice:
Time relation of the narrating action to the story event. Events can be told while they are happening (concurrently),
Time of narration
retrospectively, or prospectively.
Voice: Person
Narrator participation. A homodiegetic narrative instance is a character of the current narration (grammatical
realization typically in the first person), while a heterodiegetic narrative instance is absent from the current
narrative and not referred to. In a second-person narrative, the protagonist is the reader.
Table 1: Selected Narratological Parameters in Discourse Domain

NARRATING
das groe brasilianische Mdchen the tall
Brasilian girl
ein Beobachter an observer
metonymic eine Legende a legend
die Briefe the letters
die Orte the locations
jedem, der mich danach fragt everyone who
Addressee
asks me about it
den Eltern to the parents
Die Impulse, aus denen heraus [erzhlt wird],
Motivation
sind unterschiedlich The impulses why
something [is told] are different
Consequence/ [Ich erzhle dir das] deshalb, damit du heute
schon weit, da alles seinen Preis hat. [I tell
Aim
you this] so that you already today know that
everything has its price.
Wir haben uns bepit vor Lachen[, als Kai
erzhlte,...] We pissed ourself laughing [when
Kai told...]
ParallelEvent Whrend sie aen, [erzhlte er von seinen
Brdern.] While they were eating, [he was
talking about his brothers.]
nach zwei Schlucken Bier after two sips of beer
Time
am Abend in the evening
in der Schule at school; zu Hause at home
Place
mit fast kindlicher Begeisterung with almost
Manner
childlike enthusiasm
geheimnisvoll tuend with mysterious ado
Table 2: Fillers of the NARRATING frame in DWDS corpus
Narrative
Instance

NARRATED_LINGUISTIC_MESSAGE
TextType

Support
Topic

Linguistic
Surface
Realization

Geschichte story
Lgengeschichten cock and bull stories
Anekdoten anecdotes
Mrchen fairy tales
Trume dreams
Witze jokes
Episoden aus der Geschichte story episodes
in seinem Buch in his book
von ihrem eigenen Leben about her own life
von seinem Ausreiseantrag about his emigration application [from Eastern Germany]
[die Geschichte] eines Gastarbeiters [the
story] of a foreign worker
[Geschichten] von den Reihern [stories]
about the herons
Frauen[geschichten] women [stories]
mehr oder weniger spannende Kriegsabenteuer more or less thrilling war adventures
was ber ihre anderen Hamster something
about her other hamsters
D Von Kreta aus[, erzhlte er weiter,]
sind wir nach Rhodos gefahren.
From Crete[, he went ahead telling,]
we went to Rhodos.
[erzhlte er:] Sie waren Zwillinge.
[...] [he told:] They were twins. [...]
continued on the next page

NARRATED_LINGUISTIC_MESSAGE (ctd.)
Linguistic
Surface
Realization
(continued)

[Dieser Mann hat uns gerade erzhlt,]

da vor seinen Augen ein Toter
wiederauferstanden ist [This man has
just told us] that someone rose from the
dead right before his eyes
[Runge erzhlt,] er habe gelegentlich
eines Aufenthaltes in Kopenhagen zwei
Mnner karikiert, die spter, von der
Polizei gesucht, anhand seiner Zeichnung
ausfindig gemacht werden konnten.
[Runge tells] he had caricatured two
men during a stay in Copenhagen, who
later on, being searched for by the police,
could be found with his drawing.
Table 4: Fillers of the NARRATED frame in DWDS corpus
Classes and Relations
Instantiation
Narration
a,b
NarrativeInstance
i,j
Attribution of NarrativeInstance toldBy(a,i), toldBy(b,j)
Attribution of Narration
toldIn(b,a)
Sequence
discourse_sequence=[a,b]
Table 7: One Inner Narration; Opening Outer Narration only
Classes and Relations
Instantiation
Narration
a,b
NarrativeInstance
i,j
Attribution of NarrativeInstance toldBy(a,i), toldBy(b,j)
Attribution of Narration
toldIn(a,b)
Sequence
discourse_sequence=[a,b]
Table 8: One Inner Narration; Closing Outer Narration only

Classes and Relations

Narration
NarrativeInstance
Attribution of
NarrativeInstance
Attribution of Narration

Instantiation
a,b,c,d,e
i,j,k
toldBy(a,i), toldBy(b,j), toldBy(c,j),
toldBy(d,j), toldBy(e,k)
toldIn(b,a), toldIn(c,a), toldIn(d,a),
toldIn(e,d)
Sequence
discoursesequence=[a1,b,a2,c,a3,d1,e,d2,a4]
Table 11: Parallel Inner Narrations; Third Level

[a2 toldBy i] Marlow ceased, and sat apart [...] in the pose of a
meditating Buddha. Nobody moved [...]. We have lost the first of
the ebb, said the Director suddenly. I raised my head. The offing
was barred by a black bank of clouds, and the tranquil waterway
leading to the uttermost ends of the earth flowed sombre under an
overcast sky seemed to lead into the heart of an immense
darkness.
Figure 8: The closing part of narration a in Heart of Darkness

[a1 toldBy i] The next evening we were seated [...] in a dainty

little salon, she on a couch, I on cushions [...].
Go on, she said. I am listening.
But I dare not begin. [...].
Speak.
I obey.
[b toldBy i] Ernest-Jean Sarrasine was the only son of a
prosecuting attorney of Franche-Comte, [comment by i] I began
[...]. [b toldBy i] His father had [...] amassed a fortune [...], then
[...].
Figure 9: The same narrative instance tells two narrations (from
Sarrasine by Honor de Balzac8)

Classes and Relations

Instantiation
Narration
a,b
NarrativeInstance
i
Attribution of NarrativeInstanc
toldBy(a,i), toldBy(b,i)
Attribution of Narration
toldIn(b,a)
Sequence
discourse-sequence=[a1,b,a2]
Table 9: One Inner Narration with Constant NarrativeInstance
Classes and Relations
Instantiation
Narration
a,b,c,d
NarrativeInstance
i,j,k,l
Attribution of
toldBy(a,i), toldBy(b,j), toldBy(c,k),
NarrativeInstance
toldBy(d,l)
Attribution of Narration
toldIn(b,a), toldIn(c,b), toldIn(d,c)
Sequence
discourse-sequence=[a,b,c,d]
Table 10: Three Opening Narrations; Fourth Level

http://www.gutenberg.org/etext/1826 [10 March, 2005].